Parallel Processing

This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to use parallel processing (joblib, multiprocessing), out-of-core computing (Dask, Zarr), GPU acceleration (PyTorch, JAX), or memory-efficient strategies. Use this skill before running analyses, training models, processing large datasets, or any task where resource constraints matter.

Subagent-Driven Development is a workflow methodology for executing implementation plans by dispatching fresh subagents per task with code review between tasks. It supports sequential execution for coupled tasks, parallel execution for independent tasks, and parallel investigation for debugging multiple unrelated failures. The skill emphasizes maintaining code quality through review checkpoints while enabling fast iteration.